SOURCE-LINKED INTELLIGENCE

Dependency-Aware Trajectory Refinement for Efficient Multi-Turn Agent Fine-Tuning

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both training and inference cost. We propose viewing each trajectory as a \emph{round-level dependency DAG} that exposes which rounds are globally load-bearing for the final answer, and fine-tune agents on trajectories refined through this DAG. Given an LLM-annotated DAG, these edits are deterministic and interpretable, with optional rephrasing. Models trained on these refined trajectories consistently outperform those trained on the original trajectories

Read original source ↗ Open in workspace

recordType

paper

region

Global